融合高分辨率的珠海一号高光谱影像分类比较

Classification and Comparison of Hyperspectral Images of Zhuhai-1with High Resolution

随着遥感技术的发展,高光谱遥感卫星陆续发射,高光谱遥感在资源调查与监测中的应用也越来越广泛。资源调查和监测的基础问题是影像分类,分类精度的高低决定着资源调查和监测的准确性。但由于高光谱影像一般空间分辨率比较低,约束了其应用,分类精度也因此降低。以珠海一号高光谱影像为基础数据源,结合资源三号影像,基于像素分类和面向对象分类等分类方法,分别对资源三号未融合影像与融合影像、珠海一号与资源三号融合影像等进行分类比较。通过以上分类结果的对比,发现珠海一号影像更适合用面向对象的分类方法,并且在融合了资源三号全色影像之后,珠海一号同时具备了高光谱和高空间分辨率的特性,分类精度较之前提高了10%。

With the development of remote sensing technology,hyperspectral remote sensing satellites have been launched one after another,and they are increasingly widely used in resource investigation and monitoring.The basic problem of resource investigation and monitoring is image classification,the accuracy of classification determines the accuracy of resource investigation and monitoring.However,the spatial resolution of hyperspectral images is generally low,this constrains its applications,and the classification accuracy is reduced.In this paper,we takes the Zhuhai-1hyperspectral image as the basic data source,combinedthe ZY-3image,we compare pixel based and object-oriented,bfore and after fusion of resource 3 panchromatic image,fsed image and ZY-3image,the result shows that:Zhuhai-1image is more suitable for object-oriented classification,after fusing the panchromatic image of ZY-3,Zhuhai-1has the characteristics of hyperspectral and high spatial resolution,and the classification accuracy is 10%higher than before.